CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

handoff

Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh Claude session can continue exactly where this one left off. Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, instruction-only skill that fully specifies its deliverable through a concrete template, specific writing rules, and exact follow-up steps for the user. The main gaps are duplication between the section explanations and the template, the absence of a post-write verification checkpoint, and the fully inlined bulky template.

Suggestions

Add a verification checkpoint after writing: re-read HANDOFF.md and confirm a fresh agent could start Next Steps item 1 immediately without asking questions, per the skill's own standard of ruthlessly specific steps.

Deduplicate the "What to Capture" explanations with the Output template — either fold the guidance into the template placeholders or trim the prose sections so each item is explained once.

Consider moving the full HANDOFF.md template to a references/ file linked from SKILL.md so the ~55-line block does not consume tokens on every invocation.

DimensionReasoningScore

Conciseness

The body is mostly efficient and load-bearing, but the "What to Capture" section explanations duplicate the Output template placeholders (e.g., the Goal guidance appears in both section 1 and the template), a minor trimming opportunity. Not a 5 because the duplication means not every token earns its place; not a 3 because padding is not extensive.

4 / 5

Actionability

Fully actionable for an instruction-only skill: a copy-paste-ready HANDOFF.md template, concrete good/bad examples ("Fix the auth" is bad vs. the specific "src/auth/middleware.ts:47" example), an exact output location, and the exact phrasing for the next-session prompt.

5 / 5

Workflow Clarity

The capture → write → tell-user sequence is clear and ordered (numbered required sections, ordered After Writing steps), but there is no verification checkpoint such as re-reading the handoff to confirm Next Steps item 1 is immediately actionable. Writing HANDOFF.md is neither destructive nor batch, so the 3-cap does not apply.

4 / 5

Progressive Disclosure

Well-organized sections with clear headers and no bundle files, so everything is inline; the ~55-line template block (roughly half the document) could be externalized to a references file so it does not load on every invocation. Good structure, but not the well-signaled one-level-deep reference layout of a 5.

4 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that names a concrete artifact, enumerates its contents comprehensively, and pairs it with an explicit and natural 'Use when...' trigger clause. The only gap is a few missing spoken synonyms (e.g., "handoff", "start fresh") in the trigger coverage.

DimensionReasoningScore

Specificity

"Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps" names the concrete artifact and comprehensively enumerates what it contains, leaving no coverage gaps for this single-deliverable task. Voice is third person, so no penalty applies.

5 / 5

Completeness

Explicitly answers both what ("Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps") and when ("Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later" provides natural scenario phrases, but omits spoken keywords a user would plausibly say such as "handoff", "start fresh", or "new session".

4 / 5

Distinctiveness Conflict Risk

Generating a session-continuation handoff document is a clear niche with distinct, specific triggers (long sessions, repeated failed attempts, stepping away), creating minimal conflict risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

thedotmack/claude-mem

Path

plugin/skills/handoff/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.